Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.6113. Min Act: -0.1700
Data Index: 4002968 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4550. Min Act: -0.1700
Data Index: 4168605 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4550. Min Act: -0.1700
Data Index: 529651 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4550. Min Act: -0.1700
Data Index: 6867038 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4238. Min Act: -0.1700
Data Index: 7980332 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3925. Min Act: -0.1700
Data Index: 125813 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.4238. Min Act: -0.1700
Data Index: 7768918 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 3283470 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 283400 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 8664648 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3925. Min Act: -0.1700
Data Index: 4153711 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 1111669 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 7507901 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 2085576 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 2045407 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 5699915 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 1380556 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3613. Min Act: -0.1700
Data Index: 7403687 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 1821914 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6113. Min Range: -4.6113
Max Act: 4.3300. Min Act: -0.1700
Data Index: 6851824 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19